Research map / Probabilistic and scientific modeling / Bayesian optimization
Scalable Global Optimization via Local Bayesian Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use separate local GPs instead of one global GP | TuRBO's robot-pushing regression setup · Robot pushing | test log loss: 1.284 -> 1.174; 0.110 nats | Helped |
| Maintain 20 trust regions instead of one (ablation) | TuRBO · Robot pushing | reward | Helped |
| Maintain 20 trust regions instead of one (ablation) | TuRBO · Rover trajectory | objective value | No clear effect |
| Maintain five trust regions instead of one (ablation) | TuRBO · Cosmological constant | objective value | Helped |
| Use one trust region instead of five (ablation) | TuRBO · Cosmological constant | objective value | Hurt |
| Maintain five trust regions instead of one (ablation) | TuRBO · Lunar landing | reward | No clear effect |
| Maintain five trust regions instead of one (ablation) | TuRBO · Ackley-200 | objective value | No clear effect |
| Use large batches rather than sequential evaluations (ablation) | TuRBO-1 · Robot pushing | reward at a fixed number of batches | Helped |
| Use large batches rather than sequential evaluations (ablation) | TuRBO-1 · Robot pushing | speed-up: nearly linear | Helped |
| Use local trust-region models instead of a global GP | TuRBO · Robot pushing | optimization performance: 0.110 nats | Helped |
Closest papers by meaning
- Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Optimizing Posterior Samples for Bayesian Optimization via Rootfinding (ICLR 2025 · similarity 0.88)
- Understanding High-Dimensional Bayesian Optimization (ICML 2025 · similarity 0.88)
- BayeSQP: Bayesian Optimization through Sequential Quadratic Programming (NeurIPS 2025 · similarity 0.88)
- A General Framework for User-Guided Bayesian Optimization (ICLR 2024 · similarity 0.87)
- Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimization (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.